{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T02:46:18Z","timestamp":1784861178796,"version":"3.55.0"},"reference-count":230,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2045"],"award-info":[{"award-number":["U20B2045"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192784"],"award-info":[{"award-number":["62192784"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236003"],"award-info":[{"award-number":["62236003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Elite Scientists Sponsorship Program","award":["2023QNRC001"],"award-info":[{"award-number":["2023QNRC001"]}]},{"name":"CAST"},{"name":"NSF","award":["III-2106758"],"award-info":[{"award-number":["III-2106758"]}]},{"name":"NSF","award":["POSE-2346158"],"award-info":[{"award-number":["POSE-2346158"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tpami.2025.3548729","type":"journal-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T18:38:49Z","timestamp":1741286329000},"page":"5023-5044","source":"Crossref","is-referenced-by-count":30,"title":["Graph Foundation Models: Concepts, Opportunities and Challenges"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2437-0455","authenticated-orcid":false,"given":"Jiawei","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7821-0030","authenticated-orcid":false,"given":"Cheng","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7979-340X","authenticated-orcid":false,"given":"Zhiyuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junze","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3877-1154","authenticated-orcid":false,"given":"Yibo","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengmei","family":"Zhang","sequence":"additional","affiliation":[{"name":"China Telecom Bestpay, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9607-3551","authenticated-orcid":false,"given":"Ting","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4265-5289","authenticated-orcid":false,"given":"Yuan","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1539-7939","authenticated-orcid":false,"given":"Lichao","family":"Sun","sequence":"additional","affiliation":[{"name":"Lehigh University, Bethlehem, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3491-5968","authenticated-orcid":false,"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Illinois, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3734-0266","authenticated-orcid":false,"given":"Chuan","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref2","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref3","first-page":"61501","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3392335"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.250598"},{"key":"ref9","first-page":"2071","article-title":"Complex embeddings for simple link prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Trouillon","year":"2016"},{"key":"ref10","first-page":"3104482","article-title":"A three-way model for collective learning on multi-relational data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nickel","year":"2011"},{"key":"ref11","first-page":"2111","article-title":"Network representation learning with rich text information","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Yang","year":"2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3161804"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref14","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref15","first-page":"5171","article-title":"Link prediction based on graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2018"},{"key":"ref16","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/509"},{"key":"ref18","article-title":"On the bottleneck of graph neural networks and its practical implications","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Alon","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3290792"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02443-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3352100"},{"issue":"1","key":"ref22","first-page":"2:1","article-title":"Large language models and knowledge graphs: Opportunities and challenges","volume":"1","author":"Pan","year":"2023","journal-title":"Trans. Graph Data Knowl."},{"key":"ref23","article-title":"Graph meets LLMs: Towards large graph models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop New Front. Graph Learn.","author":"Zhang","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3129857"},{"key":"ref26","first-page":"159","article-title":"The development of social network analysis","volume":"1","author":"Freeman","year":"2004","journal-title":"A Study Sociol. Sci."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaa257"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117921"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3053765"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083269"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2985708"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3321097"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2598561"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3395804"},{"key":"ref36","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer","year":"2017"},{"key":"ref37","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton","year":"2017"},{"key":"ref38","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Velickovic","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref40","article-title":"Dropedge: Towards deep graph convolutional networks on node classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rong","year":"2020"},{"key":"ref41","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ying","year":"2021"},{"key":"ref42","first-page":"3469","article-title":"Structure-aware transformer for graph representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2022"},{"key":"ref43","first-page":"21618","article-title":"Rethinking graph transformers with spectral attention","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kreuzer","year":"2021"},{"key":"ref44","first-page":"14501","article-title":"Recipe for a general, powerful, scalable graph transformer","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ramp\u00e1\u0161ek","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219980"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/369"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.ddtec.2020.11.009"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3155478"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450068"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3172903"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1647-3"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583386"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599256"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref58","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wei","year":"2022"},{"key":"ref59","first-page":"16302","article-title":"PRODIGY: Enabling in-context learning over graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang","year":"2023"},{"key":"ref60","first-page":"30840","article-title":"Can language models solve graph problems in natural language?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref61","article-title":"A molecular multimodal foundation model associating molecule graphs with natural language","author":"Su","year":"2022"},{"key":"ref62","article-title":"Deep graph contrastive representation learning","volume-title":"ICML Workshop Graph Representation Learn. Beyond","author":"Zhu","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467186"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539321"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583379"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29264"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29112"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539249"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20333"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583353"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-demo.21"},{"key":"ref73","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref74","article-title":"LLAMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28754"},{"key":"ref76","article-title":"Harnessing explanations: LLM-to-LM interpreter for enhanced text-attributed graph representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He","year":"2024"},{"key":"ref77","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref78","first-page":"2721","article-title":"MentorGNN: Deriving curriculum for pre-training GNNs","volume-title":"Proc. Conf. Inf. Knowl. Manage.","author":"Zhou","year":"2022"},{"key":"ref79","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref80","article-title":"Deep graph infomax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107","year":"2019"},{"key":"ref81","article-title":"Variational graph auto-encoders","volume-title":"NIPS Workshop Bayesian Deep Learn.","author":"Kipf","year":"2016"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25547"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615505"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"ref85","first-page":"1150","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"You","year":"2020"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599244"},{"key":"ref87","first-page":"52464","article-title":"Universal prompt tuning for graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fang","year":"2023"},{"key":"ref88","first-page":"12","article-title":"The reduction of a graph to canonical form and the algebra which appears therein","volume":"2","author":"Weisfeiler","year":"1968","journal-title":"nti, Ser."},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3131584"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3170559"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref92","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref94","first-page":"14582","article-title":"Pure transformers are powerful graph learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim","year":"2022"},{"key":"ref95","article-title":"Graph-BERT: Only attention is needed for learning graph representations","author":"Zhang","year":"2020"},{"key":"ref96","first-page":"12559","article-title":"Self-supervised graph transformer on large-scale molecular data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rong","year":"2020"},{"key":"ref97","article-title":"Attending to graph transformers","author":"M\u00fcller","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671913"},{"key":"ref99","first-page":"4003","article-title":"FUG: Feature-universal graph contrastive pre-training for graphs with diverse node features","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhao","year":"2024"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403237"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28755"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645620"},{"key":"ref105","first-page":"10","article-title":"Replay-and-forget-free graph class-incremental learning: A task profiling and prompting approach","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Niu","year":"2024"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3419109"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709219"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482332"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467396"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645423"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29596"},{"key":"ref112","article-title":"Pre-trained hypergraph convolutional neural networks with self-supervised learning","author":"Deng","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657715"},{"key":"ref114","first-page":"41151","article-title":"Spatial-temporal graph learning with adversarial contrastive adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2023"},{"key":"ref115","first-page":"70229","article-title":"Gpt-st: Generative pre-training of spatio-temporal graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2023"},{"key":"ref116","first-page":"1955","article-title":"Language is all a graph needs","volume-title":"Proc. Eur. Conf. Field Comput. Linguistics","author":"Ye","year":"2024"},{"key":"ref117","article-title":"Gpt4graph: Can large language models understand graph structured data? An empirical evaluation and benchmarking","author":"Guo","year":"2023"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/3655103.3655110"},{"key":"ref119","first-page":"5850","article-title":"Gimlet: A unified graph-text model for instruction-based molecule zero-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhao","year":"2023"},{"key":"ref120","article-title":"Meta-transformer: A unified framework for multimodal learning","author":"Zhang","year":"2023"},{"key":"ref121","article-title":"Deberta: Decoding-enhanced bert with disentangled attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He","year":"2021"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref123","article-title":"GPT-4 technical report","year":"2023","journal-title":""},{"key":"ref124","article-title":"Pretrained language models to solve graph tasks in natural language","volume-title":"ICML 2023 Workshop Structured Probabilistic Inference Generative Model.","author":"Wenkel","year":"2023"},{"key":"ref125","article-title":"Can LLMs effectively leverage graph structural information: When and why","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Huang","year":"2023"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672010"},{"key":"ref127","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ouyang","year":"2022"},{"key":"ref128","first-page":"27730","article-title":"Zero-shot causal graph extrapolation from text via LLMs","volume-title":"Proc. Conf. Assoc. Advance. Artif. Intell. XAI4Sci Workshop","author":"Antonucci","year":"2024"},{"key":"ref129","first-page":"5753","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang","year":"2019"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1525\/9780520940420-020"},{"key":"ref131","first-page":"5628","article-title":"A theoretical analysis of contrastive unsupervised representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Saunshi","year":"2019"},{"key":"ref132","article-title":"Evaluating large language models on graphs: Performance insights and comparative analysis","author":"Liu","year":"2023"},{"key":"ref133","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1162\/tacl_a_00324","article-title":"How can we know what language models know?","volume":"8","author":"Jiang","year":"2020","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.827"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"ref136","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671709"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43418-1_10"},{"key":"ref139","article-title":"Node feature extraction by self-supervised multi-scale neighborhood prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chien","year":"2022"},{"key":"ref140","article-title":"Intruding with words: Towards understanding graph injection attacks at the text level","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lei","year":"2024"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599833"},{"key":"ref142","article-title":"One for all: Towards training one graph model for all classification tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599376"},{"key":"ref144","article-title":"Edgeformers: Graph-empowered transformers for representation learning on textual-edge networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jin","year":"2023"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635853"},{"key":"ref146","first-page":"13308","article-title":"WalkLM: A uniform language model fine-tuning framework for attributed graph embedding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tan","year":"2023"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657978"},{"key":"ref148","article-title":"Learning multiplex embeddings on text-rich networks with one text encoder","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Jin","year":"2023"},{"key":"ref149","article-title":"Large language models as topological structure enhancers for text-attributed graphs","author":"Sun","year":"2023"},{"key":"ref150","article-title":"Label-free node classification on graphs with large language models (LLMs)","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref151","first-page":"28798","article-title":"Graphformers: GNN-nested transformers for representation learning on textual graph","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang","year":"2021"},{"key":"ref152","article-title":"Learning on large-scale text-attributed graphs via variational inference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao","year":"2023"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591641"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645627"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/634"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.387"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.132"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645458"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.47"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00759-6"},{"key":"ref161","first-page":"30458","article-title":"Enhancing activity prediction models in drug discovery with the ability to understand human language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Seidl","year":"2023"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.966"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108073"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645682"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657775"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.692"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651476"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.801"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.366"},{"key":"ref170","first-page":"5950","article-title":"LLMs as zero-shot graph learners: Alignment of GNN representations with LLM token embeddings","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2024"},{"key":"ref171","first-page":"132876","article-title":"G-retriever: Retrieval-augmented generation for textual graph understanding and question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"He","year":"2024"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671987"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i16.33837"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.537"},{"key":"ref175","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hu","year":"2020"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599843"},{"key":"ref177","first-page":"60980","article-title":"Teg-db: A comprehensive dataset and benchmark of textual-edge graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2024"},{"key":"ref178","first-page":"141045","article-title":"Can large language models analyze graphs like professionals? A benchmark, datasets and models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2024"},{"key":"ref179","article-title":"Evaluating large language models at evaluating instruction following","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zeng","year":"2024"},{"key":"ref180","article-title":"Adversarial glue: A multi-task benchmark for robustness evaluation of language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2021"},{"key":"ref181","first-page":"31232","article-title":"Decodingtrust: A comprehensive assessment of trustworthiness in GPT models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1111\/nyas.15007"},{"key":"ref183","first-page":"10041","article-title":"Transformers are ssms: Generalized models and efficient algorithms through structured state space duality","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dao","year":"2024"},{"key":"ref184","first-page":"9422","article-title":"White-box transformers via sparse rate reduction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yu","year":"2024"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645571"},{"key":"ref186","first-page":"34670","article-title":"Position: Graph foundation models are already here","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mao","year":"2024"},{"key":"ref187","first-page":"50825","article-title":"Graph mixture of experts: Learning on large-scale graphs with explicit diversity modeling","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30761-2"},{"key":"ref189","first-page":"40519","article-title":"On the power of foundation models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yuan","year":"2023"},{"key":"ref190","first-page":"1","article-title":"Its all graph to me: Single-model graph representation learning on multiple domains","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Davies","year":"2023"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645439"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.189"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.632"},{"key":"ref194","article-title":"How good are GPT models at machine translation? A comprehensive evaluation","author":"Hendy","year":"2023"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1145\/3617680"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415539"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.6339\/22-JDS1047"},{"key":"ref198","article-title":"Thought propagation: An analogical approach to complex reasoning with large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2024"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2020.1166"},{"key":"ref200","article-title":"Pre-training molecular graph representation with 3D geometry","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2022"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/760"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539093"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380186"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422572"},{"key":"ref205","first-page":"20841","article-title":"Black-box tuning for language-model-as-a-service","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun","year":"2022"},{"key":"ref206","article-title":"Siren\u2019s song in the AI ocean: A survey on hallucination in large language models","author":"Zhang","year":"2023"},{"key":"ref207","article-title":"Investigating the factual knowledge boundary of large language models with retrieval augmentation","author":"Ren","year":"2023"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.136"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645703"},{"key":"ref210","first-page":"4543","article-title":"Inference attacks against graph neural networks","volume-title":"Proc. USENIX Secur.","author":"Zhang","year":"2022"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709256"},{"key":"ref212","first-page":"23768","article-title":"Be confident! towards trustworthy graph neural networks via confidence calibration","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2021"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511948"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30714-9"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645693"},{"key":"ref216","article-title":"Beyond memorization: Violating privacy via inference with large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Staab","year":"2024"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1145\/3606017"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00639"},{"key":"ref219","first-page":"22667","article-title":"Slaps: Self-supervision improves structure learning for graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fatemi","year":"2021"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26319"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3349850"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313562"},{"key":"ref224","article-title":"Graph neural networks designed for different graph types: A survey","author":"Thomas","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3340404"},{"key":"ref226","first-page":"22326","article-title":"Long range graph benchmark","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dwivedi","year":"2022"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3122899"},{"key":"ref228","first-page":"17009","article-title":"Design space for graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"You","year":"2020"},{"key":"ref229","first-page":"4465","article-title":"Distance encoding: Design provably more powerful neural networks for graph representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2020"},{"key":"ref230","first-page":"21","article-title":"Will more expressive graph neural networks do better on generative tasks?","volume-title":"Proc. Learn. Graphs Conf.","author":"Zou","year":"2024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10990047\/10915556-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10990047\/10915556.pdf?arnumber=10915556","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T04:26:43Z","timestamp":1746678403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10915556\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":230,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3548729","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}